Data Sheet 3_Liver X receptor agonist T0901317 alleviates sepsis-induced acute lung injury by enhancing macrophage autophagy.csv حسب Ben Wang (250897)

"…However, among these genes, only S100A8 that was increased in ALI and decreased markedly after T0 treatment exhibited a negative correlation with T0. …"

FFD – main effect, original fibrosis burden. حسب Åshild Telle (22794721)

Analysis of errors of the AI model on accuracy and decision times for different tasks during the retrospective reader study. (a) حسب Kerol Djoumessi (21349992)

Algorithm training accuracy experiments. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

Repeat the detection experiment. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

Detection network structure with IRAU [34]. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

Ablation experiments of various block. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

Kappa coefficients for different algorithms. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

The structure of ASPP+ block. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

The structure of attention gate block [31]. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

DSC block and its application network structure. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

The structure of multi-scale residual block [30]. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

The structure of IRAU and Res2Net+ block [22]. حسب Yingying Liu (360782)

"…The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. …"

Ablation Experiment GradCAM Heatmap. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Space-to-depth convolution. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Data augmentation. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Side angle tea picking. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Comparison results of ablation experiments. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Table of dataset division. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"

Striking image. حسب Chunhua Yang (346871)

"…The experimental results demonstrate that when compared to YOLOv10, S-YOLOv10-ASI shows significant improvements across various metrics. Specifically, Bounding Box Regression Loss decreases by over 30% in the training set, while Classification Loss and Bounding Box Regression Loss drop by more than 60% in the validation set. …"